A SIGN LANGUAGE RECOGNITION SYSTEM

Sign languages are a set of predefined languages that use the visual-manual modality to convey meaningful information. Sign language is an essential tool to bridge the communication gap between normal and hearing-impaired people. This project aims to identify alphabets in Indian sign language from the corresponding gestures. The main goal of this project is to create a deep learning-based application that offers a sign language translator. In this project, we use a CNN algorithm for the recognition of sign language. We used the Kaggle dataset for sign language recognition. The size of the dataset is 281.95 MB. It contains 35 directories in 26 characters (A to Z) and 9 numeric signs (1 to 9).In this project, we designed a system that will be able to recognize hand gestures by using deep learning architecture. In this project, we study the different types of hand features for the problem of sign language recognition using a Convolutional Neural Network.